Hello, I am Zeru, a first year Ph.D. student in Rutgers University. I am honored to be guided by Prof.Ruixiang Tang. I will receive my BE degree in Software Engineering at Dalian University of Technology

My research interests mainly focus on:

• AI interpretability: I aim to leverage interpretability analysis of LLMs and VLMs to identify lightweight, efficient, and training-free methods that can generally enhance their performance.
• LLM/VLM Reasoning: I am highly interested in reasoning within LLMs and VLMs. My work explores post-training methods, such as reinforcement learning–based optimization, as well as training-free approaches to improve their reasoning capabilities.
• LLM-based Multi-Agent System: I am especially interested in the memory mechanisms of LLM-based agent systems.

Meanwhil, I’ve got a bunch of hobbies, likes soccer, traditional Chinese calligraphy, traveling and mixing drinks. By the way I am a big Manchester United fan.

My CV is here: Zeru’s CV

I am always open to research collaborations. If you are interested in my previous work or would like to discuss potential ideas, please feel free to contact me.

🔥 News

📷 Publication

ICLR2025

From Commands to Prompts: LLM-based Semantic File System
Zeru Shi*, Kai Mei*, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang

[Arxiv], [GitHub]

IEEE TCSVT(IF=11.1)

SeFENet: Robust Deep Homography Estimation via Semantic-Driven Feature Enhancement
Zeru Shi, Zengxi Zhang, Kemeng Cui, Ruizhe An, Jinyuan Liu, Zhiying Jiang

[Arxiv]

EMNLP2025 (Main)

Castle: Causal Cascade Updates in Relational Databases with Large Language Models
Yongye Su, Yucheng Zhang, Zeru Shi, Bruno Ribeiro, Elisa Bertino

[Arxiv]

📝 Pre-Print

Arxiv

Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning
Zeru Shi, Yingjia Wan, Zhenting Wang, Qifan Wang, Fan Yang, Elisa Kreiss, Ruixiang Tang

[Arxiv], [GitHub]

Arxiv

Auto-Prompt Generation is Not Robust:Prompt Optimization Driven by Pseudo Gradient
Zeru Shi, Zhenting Wang, Yongye Su, Weidi Luo, Hang Gao, Fan Yang, Ruixiang Tang, Yongfeng Zhang

[Arxiv], [GitHub]

🎖 Honors and Awards

• 2025.10 Rutgers Climate and Energy Institute (RCEI) Fellowship, USA
• 2025.6 Dalian excellent undergraduate graduates, China
• 2024.11 National Scholarship, China
• 2023.9 Special scholarship of NOK Corporation, Japan

📖 Educations

• 2021.09 - 2025.06, Dalian University of Technology, ISE, Liaoning, Undergraduate
• 2025.09 - Present, Rutgers University, Computer Science, New Brunswick, Ph.D.

💻 Internships

• 2024.10 - 2025.4, Shanghai AI Laboratory, Shanghai
• 2024.2 - 2024.3, Li Auto.Inc, Beijing